Noometry

Model comparison

GLM-5.2 vs Mistral Small 4

GLM-5.2 has enough public results to be ranked (#38); Mistral Small 4 does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

GLM-5.2 Z.ai (Zhipu)

50.9

Rank #38 Confirmed

Mistral Small 4 Mistral AI

30.2

Unranked Sparse

Summary

  • They share 1 benchmark with published results for both. GLM-5.2 scores higher in 1 category and Mistral Small 4 in 0 categories; one gap is clear of the uncertainty.
  • The widest gap is in reasoning, where GLM-5.2 leads 42.1 to 21.2.
  • The biggest single-benchmark swing is Kagi LLM Benchmark: 62.6% for GLM-5.2 and 40.5% for Mistral Small 4.
  • Mistral Small 4 is cheaper at $0.075 / $0.30 per million input/output tokens, against $1.40 / $4.40 for GLM-5.2.
  • GLM-5.2 accepts more context: 1M tokens versus 262K.

Side by side

GLM-5.2Mistral Small 4
ProviderZ.ai (Zhipu)Mistral AI
Noometry Index50.930.2
Released2026-06-13—
WeightsOpenOpen
Context window1M262K
Max output131K210K
Input $ / M tokens$1.40$0.075
Output $ / M tokens$4.40$0.30
Results tracked501

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Not comparable

GLM-5.2: 50.9 (#37), Mistral Small 4: —

BenchmarkGLM-5.2Mistral Small 4
SWE-bench Verified78.7%—
DeepSWE43.8%—
FrontierCode24.5%—
LMArena WebDev1604—
SciCode50.5%—
WeirdML70.1%—
LMArena Coding1484—
ALE-Bench1,047—

Agentic & Tool Use Not comparable

GLM-5.2: 31.6 (#63), Mistral Small 4: —

BenchmarkGLM-5.2Mistral Small 4
τ²-bench Banking37.1%—
PostTrainBench31.7%—
GBAEval0%—
Vending-Bench 28,314—

Reasoning GLM-5.2 leads

GLM-5.2: 42.1 (#46), Mistral Small 4: 21.2

BenchmarkGLM-5.2Mistral Small 4
Kagi LLM Benchmark62.6%40.5%
ARC-AGI-222.8%—
SimpleBench58.8%—
NYT Connections (extended)74.3%—
ARC-AGI-177%—
CritPt20.9%—
Chess Puzzles21%—
EBR-Bench9.5%—
LMArena Hard Prompts1480—
Mystery Game Puzzles19%—
DTBench93.6%—
LMCA45.8%—
Surface Evolver Bench55.6%—
Epoch Capabilities Index151.76—

Math Not comparable

GLM-5.2: 55.4 (#35), Mistral Small 4: —

BenchmarkGLM-5.2Mistral Small 4
FrontierMath (Tiers 1-3)59.2%—
FrontierMath Tier 429.3%—
MathArena Final-Answer Competitions67.6%—
OTIS Mock AIME 2024-202586.4%—
ProofBench35%—
LMArena Math1482—

Knowledge Not comparable

GLM-5.2: 57.1 (#36), Mistral Small 4: —

BenchmarkGLM-5.2Mistral Small 4
GPQA Diamond91.9%—
SimpleQA Verified34.2%—
LMArena Expert1484—

Multilingual Not comparable

GLM-5.2: 56.0 (#25), Mistral Small 4: —

BenchmarkGLM-5.2Mistral Small 4
LMArena Non-English1459—
LMArena Chinese1518—
LMArena French1476—
LMArena German1470—
LMArena Japanese1451—
LMArena Korean1445—
LMArena Russian1467—
LMArena Spanish1477—

Instruction Following Not comparable

GLM-5.2: 77.1 (#32), Mistral Small 4: —

BenchmarkGLM-5.2Mistral Small 4
LMArena Instruction Following1465—

Long Context Not comparable

GLM-5.2: 45.3 (#43), Mistral Small 4: —

BenchmarkGLM-5.2Mistral Small 4
LMArena Longer Query1479—

Writing & Preference Not comparable

GLM-5.2: 70.7 (#20), Mistral Small 4: —

BenchmarkGLM-5.2Mistral Small 4
LMArena Text1470—
LMArena Creative Writing1465—
EQ-Bench Creative Writing1757—
EQ-Bench 41222—
LMArena Multi-Turn1468—

Frequently asked questions

Is GLM-5.2 better than Mistral Small 4?

GLM-5.2 has enough public results to be ranked (#38); Mistral Small 4 does not yet, so treat this comparison as directional.

Which is cheaper, GLM-5.2 or Mistral Small 4?

Mistral Small 4 is cheaper. It lists at $0.075 per million input tokens and $0.30 per million output tokens; GLM-5.2 lists at $1.40 and $4.40.

Which has the bigger context window?

GLM-5.2 does, with 1M tokens against 262K.

How many benchmarks do GLM-5.2 and Mistral Small 4 share?

1 benchmark has published results for both models. GLM-5.2 has 50 scored results on Noometry and Mistral Small 4 has 1.

Related comparisons

Go deeper